Household flow detection using FEAT (flow estimating accelerometer-thermometer) device

Abstract

The use of IoT devices in water end use disaggregation verification is an emerging field which offers benefits over conventional approaches, in terms of cost, accuracy and scalability. Having reliably disaggregated water appliance consumption data will enable smart water meter data to be used in household water conservation approaches and for understanding water consumption behaviours. The FEAT device provides a low cost, easily applied and scalable solution that is demonstrated to work even for very low flow conditions of 0.03 l/s. The FEAT device is a combination of a battery, Wi-fi board and MPU6050 sensors providing multi-modal accelerometer and thermometer data. The study places 7 of these FEAT devices onto hot and cold water pipes leading to a shower, which is operated 4 times in a high flow situation, 0.13 l/s, and 4 times in a low flow situation, 0.03 l/s. The data is then analysed and compared with a flow logger to determine if the FEAT device can detect when a domestic appliance is using water. There are limiting cases where the level of noise or external interference limits distorts the data, obscuring the distinguishable peaks in the data due to the similarity of the values. By using high and low pass filtering methods it was possible to enhance the peaks but there are still situations where peaks cannot be detected: for example, if a rigid pipe is not able to vibrate easily or if a hot water boiler is not triggered due to the low flow rate. However, the results show it should be possible to overcome these limiting cases, as it is much less likely for both the vibration and temperature data to be adversely affected by noise or external influences simultaneously, therefore decreasing the effect of noise and external influences. In conclusion, this research paper demonstrates that FEAT devices are a low cost, easily applied and scalable solution for detecting flow. By using high and low pass filtering, placing sensors on freely moving pipes and through the use of multi-modal verification, the FEAT device is shown to work on both metal and plastic pipes even in the lowest flow situations of 0.03 l/s. Therefore the FEAT device is a suitable solution for appliance identification in disaggregation verification datasets.